adirik / flux-cinestill

Flux lora, use "CNSTLL" to trigger

Warm

Public
85.8K runs
H100

Run with an API

Playground API Examples README Versions

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:0a6ad486

zjanp6dhg5rm00chghnb9bqj1m

Status

Succeeded

Source

Web

Hardware

H100

Total duration

27.0s

Created

7 months ago by @adirik

Input

model: dev
prompt: CNSTLL, Road trip, view through car window of desert highway
lora_scale: 0.6
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "CNSTLL, Road trip, view through car window of desert highway\n",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "CNSTLL, Road trip, view through car window of desert highway\n",
      lora_scale: 0.6,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "CNSTLL, Road trip, view through car window of desert highway\n",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "CNSTLL, Road trip, view through car window of desert highway\\n",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T12:44:57.435576Z",
  "created_at": "2024-08-24T12:44:30.465000Z",
  "data_removed": false,
  "error": null,
  "id": "zjanp6dhg5rm00chghnb9bqj1m",
  "input": {
    "model": "dev",
    "prompt": "CNSTLL, Road trip, view through car window of desert highway\n",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 57711\nPrompt: CNSTLL, Road trip, view through car window of desert highway\ntxt2img mode\nUsing dev model\nfree=9659731640320\nDownloading weights\n2024-08-24T12:44:30Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpw4usuaxz/weights url=https://replicate.delivery/yhqm/GLO5igfTLkwNb6cZ7GvWXQ6e7BMvPZWOyJdgyWfDhHprqwrmA/trained_model.tar\n2024-08-24T12:44:33Z | INFO  | [ Complete ] dest=/tmp/tmpw4usuaxz/weights size=\"688 MB\" total_elapsed=3.324s url=https://replicate.delivery/yhqm/GLO5igfTLkwNb6cZ7GvWXQ6e7BMvPZWOyJdgyWfDhHprqwrmA/trained_model.tar\nDownloaded weights in 3.37s\nLoaded LoRAs in 18.57s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.54it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.97it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.76it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.67it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.59it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.58it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.56it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.55it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.54it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.52it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.55it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.54it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.54it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.54it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.54it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.54it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.53it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.54it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.54it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.54it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.53it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.54it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.53it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.56it/s]",
  "metrics": {
    "predict_time": 26.959945308,
    "total_time": 26.970576
  },
  "output": [
    "https://replicate.delivery/yhqm/WGqB1k5eQuQTVSfffr8RfI4qs6PcNyZesqN5MKXnegR0kP8qJA/out-0.webp"
  ],
  "started_at": "2024-08-24T12:44:30.475631Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zjanp6dhg5rm00chghnb9bqj1m",
    "cancel": "https://api.replicate.com/v1/predictions/zjanp6dhg5rm00chghnb9bqj1m/cancel"
  },
  "version": "0a6ad486c5589dd78647fb44f0527bcae57f112e49b722455b289baa897232c5"
}

Generated in

27.0 seconds

Tweak it Share Report

Using seed: 57711
Prompt: CNSTLL, Road trip, view through car window of desert highway
txt2img mode
Using dev model
free=9659731640320
Downloading weights
2024-08-24T12:44:30Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpw4usuaxz/weights url=https://replicate.delivery/yhqm/GLO5igfTLkwNb6cZ7GvWXQ6e7BMvPZWOyJdgyWfDhHprqwrmA/trained_model.tar
2024-08-24T12:44:33Z | INFO  | [ Complete ] dest=/tmp/tmpw4usuaxz/weights size="688 MB" total_elapsed=3.324s url=https://replicate.delivery/yhqm/GLO5igfTLkwNb6cZ7GvWXQ6e7BMvPZWOyJdgyWfDhHprqwrmA/trained_model.tar
Downloaded weights in 3.37s
Loaded LoRAs in 18.57s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.54it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.97it/s]
 11%|█         | 3/28 [00:00<00:06,  3.76it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.67it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.59it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.58it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.56it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.55it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.54it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.52it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.55it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.54it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.54it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.54it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.54it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.54it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.53it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.54it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.54it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.54it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.53it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.54it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.54it/s]
100%|██████████| 28/28 [00:07<00:00,  3.53it/s]
100%|██████████| 28/28 [00:07<00:00,  3.56it/s]

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

k8babgk525rm20chgk99k2cwy8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

18.6s

Created

7 months ago

Input

model: dev
prompt: in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T
lora_scale: 0.6
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T",
      lora_scale: 0.6,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T14:38:05.249513Z",
  "created_at": "2024-08-24T14:37:46.641000Z",
  "data_removed": false,
  "error": null,
  "id": "k8babgk525rm20chgk99k2cwy8",
  "input": {
    "model": "dev",
    "prompt": "in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 23954\nPrompt: in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T\ntxt2img mode\nUsing dev model\nfree=9767470870528\nDownloading weights\n2024-08-24T14:37:46Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpbrncmfdz/weights url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar\n2024-08-24T14:37:48Z | INFO  | [ Complete ] dest=/tmp/tmpbrncmfdz/weights size=\"172 MB\" total_elapsed=1.616s url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar\nDownloaded weights in 1.65s\nLoaded LoRAs in 10.21s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.52it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.96it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.75it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.66it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.59it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.57it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.56it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.55it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.55it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.54it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.54it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.54it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.54it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.52it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.52it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.53it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.52it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.51it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.53it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.53it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.52it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.53it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.53it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.51it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 18.598344056,
    "total_time": 18.608513
  },
  "output": [
    "https://replicate.delivery/yhqm/HV9IE99vOlK3ERSVZ8l8NZxlMZbVzAzez2MnXMjRn6xmE9qJA/out-0.webp"
  ],
  "started_at": "2024-08-24T14:37:46.651169Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/k8babgk525rm20chgk99k2cwy8",
    "cancel": "https://api.replicate.com/v1/predictions/k8babgk525rm20chgk99k2cwy8/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

18.6 seconds

Tweak it Share Report

Using seed: 23954
Prompt: in the style of CNSTLL, a woman hiking at dusk, photorealistic, cinestill 800T
txt2img mode
Using dev model
free=9767470870528
Downloading weights
2024-08-24T14:37:46Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpbrncmfdz/weights url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar
2024-08-24T14:37:48Z | INFO  | [ Complete ] dest=/tmp/tmpbrncmfdz/weights size="172 MB" total_elapsed=1.616s url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar
Downloaded weights in 1.65s
Loaded LoRAs in 10.21s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.52it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.96it/s]
 11%|█         | 3/28 [00:00<00:06,  3.75it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.66it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.59it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.57it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.56it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.55it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.55it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.54it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.54it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.54it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.54it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.52it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.52it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.53it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.52it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.51it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.53it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.53it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.52it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.53it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.53it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.51it/s]
100%|██████████| 28/28 [00:07<00:00,  3.52it/s]
100%|██████████| 28/28 [00:07<00:00,  3.55it/s]

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

rathzs9kfxrm00chgk9rnj321w

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.5s

Created

7 months ago

Input

model: dev
prompt: in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T
lora_scale: 0.6
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
      lora_scale: 0.6,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T14:38:47.964812Z",
  "created_at": "2024-08-24T14:38:39.487000Z",
  "data_removed": false,
  "error": null,
  "id": "rathzs9kfxrm00chgk9rnj321w",
  "input": {
    "model": "dev",
    "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 51759\nPrompt: in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T\ntxt2img mode\nUsing dev model\nWeights already loaded\nLoaded LoRAs in 0.04s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.52it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.94it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.74it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.66it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.61it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.58it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.56it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.55it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.54it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.54it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.54it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.54it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.51it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.53it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.53it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.53it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.52it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.52it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.52it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.53it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.52it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.51it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.51it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.52it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 8.467421274,
    "total_time": 8.477812
  },
  "output": [
    "https://replicate.delivery/yhqm/v3ZpxG5gyA50JR1iiWanP1avoGFMOVf0fYGXOeU6DfKfORvaC/out-0.webp"
  ],
  "started_at": "2024-08-24T14:38:39.497391Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/rathzs9kfxrm00chgk9rnj321w",
    "cancel": "https://api.replicate.com/v1/predictions/rathzs9kfxrm00chgk9rnj321w/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

8.5 seconds

Tweak it Share Report

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

ebhsqv3dh1rm40chgk8bx8s66c

Status

Succeeded

Source

Web

Hardware

H100

Total duration

18.4s

Created

7 months ago

Input

model: dev
prompt: in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic
lora_scale: 0.6
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic",
      lora_scale: 0.6,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T14:35:56.151735Z",
  "created_at": "2024-08-24T14:35:37.736000Z",
  "data_removed": false,
  "error": null,
  "id": "ebhsqv3dh1rm40chgk8bx8s66c",
  "input": {
    "model": "dev",
    "prompt": "in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 33915\nPrompt: in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic\ntxt2img mode\nUsing dev model\nfree=9260846817280\nDownloading weights\n2024-08-24T14:35:37Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpbtq2xt5j/weights url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar\n2024-08-24T14:35:39Z | INFO  | [ Complete ] dest=/tmp/tmpbtq2xt5j/weights size=\"172 MB\" total_elapsed=1.549s url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar\nDownloaded weights in 1.58s\nLoaded LoRAs in 10.00s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.53it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.97it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.77it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.68it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.60it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.59it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.57it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.56it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.56it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.56it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.55it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.55it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.54it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.55it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.54it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.55it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.54it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.54it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.54it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.53it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.54it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.55it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.57it/s]",
  "metrics": {
    "predict_time": 18.408150834,
    "total_time": 18.415735
  },
  "output": [
    "https://replicate.delivery/yhqm/KAdm9lK2TNYAGR2zTQKHDrzqbG51UvD2Nz0tWATMyeglD9qJA/out-0.webp"
  ],
  "started_at": "2024-08-24T14:35:37.743584Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ebhsqv3dh1rm40chgk8bx8s66c",
    "cancel": "https://api.replicate.com/v1/predictions/ebhsqv3dh1rm40chgk8bx8s66c/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

18.4 seconds

Tweak it Share Report

Using seed: 33915
Prompt: in the style of CNSTLL, an urban landscape with street sellers and a fish market at night, photorealistic
txt2img mode
Using dev model
free=9260846817280
Downloading weights
2024-08-24T14:35:37Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpbtq2xt5j/weights url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar
2024-08-24T14:35:39Z | INFO  | [ Complete ] dest=/tmp/tmpbtq2xt5j/weights size="172 MB" total_elapsed=1.549s url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar
Downloaded weights in 1.58s
Loaded LoRAs in 10.00s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.53it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.97it/s]
 11%|█         | 3/28 [00:00<00:06,  3.77it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.68it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.60it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.59it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.57it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.56it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.56it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.56it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.55it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.55it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.54it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.55it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.54it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.55it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.54it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.54it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.54it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.53it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.54it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.55it/s]
100%|██████████| 28/28 [00:07<00:00,  3.54it/s]
100%|██████████| 28/28 [00:07<00:00,  3.57it/s]

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

0pdag5vzthrm00chgkbs9a8c3c

Status

Succeeded

Source

Web

Hardware

H100

Total duration

22.1s

Created

7 months ago

Input

model: dev
prompt: in the style of CNSTLL, a group of people talking and drinking beer at the pub in front a window, cinestill 800T, photorealistic
lora_scale: 0.6
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "in the style of CNSTLL, a group of people talking and drinking beer at the pub in front a window, cinestill 800T, photorealistic",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "in the style of CNSTLL, a group of people talking and drinking beer at the pub in front a window, cinestill 800T, photorealistic",
      lora_scale: 0.6,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "in the style of CNSTLL, a group of people talking and drinking beer at the pub in front a window, cinestill 800T, photorealistic",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "in the style of CNSTLL, a group of people talking and drinking beer at the pub in front a window, cinestill 800T, photorealistic",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T14:43:43.227045Z",
  "created_at": "2024-08-24T14:43:21.172000Z",
  "data_removed": false,
  "error": null,
  "id": "0pdag5vzthrm00chgkbs9a8c3c",
  "input": {
    "model": "dev",
    "prompt": "in the style of CNSTLL, a group of people talking and drinking beer at the pub in front a window, cinestill 800T, photorealistic",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 50680\nPrompt: in the style of CNSTLL, a group of people talking and drinking beer at the pub in front a window, cinestill 800T, photorealistic\ntxt2img mode\nUsing dev model\nLoaded LoRAs in 10.11s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.54it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.91it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.72it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.63it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.59it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.56it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.54it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.53it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.53it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.51it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.51it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.51it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.51it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.51it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.50it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.50it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.50it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.50it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.50it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.50it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.50it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.50it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.50it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.50it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.50it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.50it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.50it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.50it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]",
  "metrics": {
    "predict_time": 18.577725171,
    "total_time": 22.055045
  },
  "output": [
    "https://replicate.delivery/yhqm/PByDqy7naMJJAlcBjdaQRkVLBYEKCgXYzmiI3Re9sR3PH9qJA/out-0.webp"
  ],
  "started_at": "2024-08-24T14:43:24.649320Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/0pdag5vzthrm00chgkbs9a8c3c",
    "cancel": "https://api.replicate.com/v1/predictions/0pdag5vzthrm00chgkbs9a8c3c/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

18.6 seconds

Tweak it Share Report

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

y65k0davq9rm60chgkdrkbb9gc

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.2s

Created

7 months ago

Input

model: dev
prompt: in the style of CNSTLL , urban landscape, people fishing on Galata bridge in Istanbul at night
lora_scale: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "in the style of CNSTLL , urban landscape, people fishing on Galata bridge in Istanbul at night",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "in the style of CNSTLL , urban landscape, people fishing on Galata bridge in Istanbul at night",
      lora_scale: 1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "in the style of CNSTLL , urban landscape, people fishing on Galata bridge in Istanbul at night",
        "lora_scale": 1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "in the style of CNSTLL , urban landscape, people fishing on Galata bridge in Istanbul at night",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T14:47:51.268900Z",
  "created_at": "2024-08-24T14:47:34.074000Z",
  "data_removed": false,
  "error": null,
  "id": "y65k0davq9rm60chgkdrkbb9gc",
  "input": {
    "model": "dev",
    "prompt": "in the style of CNSTLL , urban landscape, people fishing on Galata bridge in Istanbul at night",
    "lora_scale": 1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 19502\nPrompt: in the style of CNSTLL , urban landscape, people fishing on Galata bridge in Istanbul at night\ntxt2img mode\nUsing dev model\nLoaded LoRAs in 9.07s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.66it/s]\n  7%|▋         | 2/28 [00:00<00:06,  4.21it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.95it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.84it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.77it/s]\n 21%|██▏       | 6/28 [00:01<00:05,  3.73it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.72it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.70it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.69it/s]\n 36%|███▌      | 10/28 [00:02<00:04,  3.68it/s]\n 39%|███▉      | 11/28 [00:02<00:04,  3.68it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.68it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.67it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.67it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.68it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.68it/s]\n 61%|██████    | 17/28 [00:04<00:02,  3.67it/s]\n 64%|██████▍   | 18/28 [00:04<00:02,  3.67it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.68it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.68it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.67it/s]\n 79%|███████▊  | 22/28 [00:05<00:01,  3.67it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.68it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.68it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.68it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.67it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.68it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.68it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.70it/s]",
  "metrics": {
    "predict_time": 17.186433884,
    "total_time": 17.1949
  },
  "output": [
    "https://replicate.delivery/yhqm/0okKZOOvyUZDGFz5VFufOYFjwCKIrNQvQ4LeSGyz4jrXS6VTA/out-0.webp"
  ],
  "started_at": "2024-08-24T14:47:34.082466Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/y65k0davq9rm60chgkdrkbb9gc",
    "cancel": "https://api.replicate.com/v1/predictions/y65k0davq9rm60chgkdrkbb9gc/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

17.2 seconds

Tweak it Share Report

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

z90tbfk47drm20chgkg9fxb11r

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.1s

Created

7 months ago

Input

model: dev
prompt: in the style of CNSTLL , photo of New York City at night, 4k
lora_scale: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 2.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "in the style of CNSTLL , photo of New York City at night, 4k",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "in the style of CNSTLL , photo of New York City at night, 4k",
      lora_scale: 1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 2.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "in the style of CNSTLL , photo of New York City at night, 4k",
        "lora_scale": 1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 2.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "in the style of CNSTLL , photo of New York City at night, 4k",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T14:53:20.988723Z",
  "created_at": "2024-08-24T14:53:03.931000Z",
  "data_removed": false,
  "error": null,
  "id": "z90tbfk47drm20chgkg9fxb11r",
  "input": {
    "model": "dev",
    "prompt": "in the style of CNSTLL , photo of New York City at night, 4k",
    "lora_scale": 1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 2.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 63529\nPrompt: in the style of CNSTLL , photo of New York City at night, 4k\ntxt2img mode\nUsing dev model\nLoaded LoRAs in 8.90s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.69it/s]\n  7%|▋         | 2/28 [00:00<00:06,  4.25it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.96it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.83it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.78it/s]\n 21%|██▏       | 6/28 [00:01<00:05,  3.74it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.72it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.70it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.69it/s]\n 36%|███▌      | 10/28 [00:02<00:04,  3.69it/s]\n 39%|███▉      | 11/28 [00:02<00:04,  3.68it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.67it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.68it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.68it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.67it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.67it/s]\n 61%|██████    | 17/28 [00:04<00:02,  3.67it/s]\n 64%|██████▍   | 18/28 [00:04<00:02,  3.68it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.67it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.66it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.67it/s]\n 79%|███████▊  | 22/28 [00:05<00:01,  3.67it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.67it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.66it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.67it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.67it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.67it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.67it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.70it/s]",
  "metrics": {
    "predict_time": 17.048015349,
    "total_time": 17.057723
  },
  "output": [
    "https://replicate.delivery/yhqm/bYobZuwZkOaZBBeMz0crqzyBdUliW53ia3s3MSpZJ6KwL9qJA/out-0.webp"
  ],
  "started_at": "2024-08-24T14:53:03.940708Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/z90tbfk47drm20chgkg9fxb11r",
    "cancel": "https://api.replicate.com/v1/predictions/z90tbfk47drm20chgkg9fxb11r/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

17.1 seconds

Tweak it Share Report

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

rathzs9kfxrm00chgk9rnj321w

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.5s

Created

7 months ago

Input

model: dev
prompt: in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T
lora_scale: 0.6
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
      lora_scale: 0.6,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T14:38:47.964812Z",
  "created_at": "2024-08-24T14:38:39.487000Z",
  "data_removed": false,
  "error": null,
  "id": "rathzs9kfxrm00chgk9rnj321w",
  "input": {
    "model": "dev",
    "prompt": "in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 51759\nPrompt: in the style of CNSTLL, a white car parked in front of a gas station, night time, cinestill 800T\ntxt2img mode\nUsing dev model\nWeights already loaded\nLoaded LoRAs in 0.04s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.52it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.94it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.74it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.66it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.61it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.58it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.56it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.55it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.54it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.54it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.54it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.54it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.51it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.53it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.53it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.53it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.52it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.52it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.52it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.53it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.52it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.51it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.51it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.52it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 8.467421274,
    "total_time": 8.477812
  },
  "output": [
    "https://replicate.delivery/yhqm/v3ZpxG5gyA50JR1iiWanP1avoGFMOVf0fYGXOeU6DfKfORvaC/out-0.webp"
  ],
  "started_at": "2024-08-24T14:38:39.497391Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/rathzs9kfxrm00chgk9rnj321w",
    "cancel": "https://api.replicate.com/v1/predictions/rathzs9kfxrm00chgk9rnj321w/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

8.5 seconds

Tweak it Share Report

Prediction

adirik/flux-cinestill:216a43b9

Model

adirik/flux-cinestill:216a43b9

8bgmdxj5d1rm60chgm0rytva98

Status

Succeeded

Source

Web

Hardware

H100

Total duration

19.4s

Created

7 months ago

Input

model: dev
prompt: CNSTLL, portrait of a woman standing against a door, night time, high resolution, 4k, cinestill 800t
lora_scale: 0.6
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
extra_lora_scale: 0.8
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "CNSTLL, portrait of a  woman standing against a door, night time, high resolution, 4k, cinestill 800t\n",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
  {
    input: {
      model: "dev",
      prompt: "CNSTLL, portrait of a  woman standing against a door, night time, high resolution, 4k, cinestill 800t\n",
      lora_scale: 0.6,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/flux-cinestill:216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    input={
        "model": "dev",
        "prompt": "CNSTLL, portrait of a  woman standing against a door, night time, high resolution, 4k, cinestill 800t\n",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run adirik/flux-cinestill using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f",
    "input": {
      "model": "dev",
      "prompt": "CNSTLL, portrait of a  woman standing against a door, night time, high resolution, 4k, cinestill 800t\\n",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-08-24T15:29:18.125404Z",
  "created_at": "2024-08-24T15:28:58.728000Z",
  "data_removed": false,
  "error": null,
  "id": "8bgmdxj5d1rm60chgm0rytva98",
  "input": {
    "model": "dev",
    "prompt": "CNSTLL, portrait of a  woman standing against a door, night time, high resolution, 4k, cinestill 800t\n",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 4506\nPrompt: CNSTLL, portrait of a  woman standing against a door, night time, high resolution, 4k, cinestill 800t\ntxt2img mode\nUsing dev model\nfree=9839779209216\nDownloading weights\n2024-08-24T15:28:58Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpdr4ixfvh/weights url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar\n2024-08-24T15:29:00Z | INFO  | [ Complete ] dest=/tmp/tmpdr4ixfvh/weights size=\"172 MB\" total_elapsed=2.118s url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar\nDownloaded weights in 2.15s\nLoaded LoRAs in 11.04s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.55it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.98it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.78it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.69it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.64it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.61it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.59it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.58it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.57it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.57it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.56it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.56it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.56it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.56it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.56it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.55it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.55it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.55it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.55it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.55it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.55it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.55it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.55it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.55it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.55it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.55it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.56it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.58it/s]",
  "metrics": {
    "predict_time": 19.385723191,
    "total_time": 19.397404
  },
  "output": [
    "https://replicate.delivery/yhqm/uzYBDUdl3qqGEZQRLr310BKloBcEeCapyiLleSCd7O5N56VTA/out-0.webp"
  ],
  "started_at": "2024-08-24T15:28:58.739681Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/8bgmdxj5d1rm60chgm0rytva98",
    "cancel": "https://api.replicate.com/v1/predictions/8bgmdxj5d1rm60chgm0rytva98/cancel"
  },
  "version": "216a43b9975de9768114644bbf8cd0cba54a923c6d0f65adceaccfc9383a938f"
}

Generated in

19.4 seconds

Tweak it Share Report

Using seed: 4506
Prompt: CNSTLL, portrait of a  woman standing against a door, night time, high resolution, 4k, cinestill 800t
txt2img mode
Using dev model
free=9839779209216
Downloading weights
2024-08-24T15:28:58Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpdr4ixfvh/weights url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar
2024-08-24T15:29:00Z | INFO  | [ Complete ] dest=/tmp/tmpdr4ixfvh/weights size="172 MB" total_elapsed=2.118s url=https://replicate.delivery/yhqm/3vhWyl3iACrCN9x53rEu7Lwit5hzZ9qDrKVi0wngSrNNheqJA/trained_model.tar
Downloaded weights in 2.15s
Loaded LoRAs in 11.04s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.55it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.98it/s]
 11%|█         | 3/28 [00:00<00:06,  3.78it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.69it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.64it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.61it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.59it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.58it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.57it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.57it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.56it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.56it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.56it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.56it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.56it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.55it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.55it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.55it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.55it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.55it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.55it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.55it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.55it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.55it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  3.55it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.55it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.56it/s]
100%|██████████| 28/28 [00:07<00:00,  3.55it/s]
100%|██████████| 28/28 [00:07<00:00,  3.58it/s]

Want to make some of these yourself?

Run this model

adirik / flux-cinestill

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (zjanp6dhg5rm00chghnb9bqj1m)

Logs (k8babgk525rm20chgk99k2cwy8)

Logs (rathzs9kfxrm00chgk9rnj321w)

Logs (ebhsqv3dh1rm40chgk8bx8s66c)

Logs (0pdag5vzthrm00chgkbs9a8c3c)

Logs (y65k0davq9rm60chgkdrkbb9gc)

Logs (z90tbfk47drm20chgkg9fxb11r)

Logs (rathzs9kfxrm00chgk9rnj321w)

Logs (8bgmdxj5d1rm60chgm0rytva98)